Zobrazeno 1 - 10
of 707
pro vyhledávání: '"Li, Qingyuan"'
We introduce Integer Scale, a novel post-training quantization scheme for large language models that effectively resolves the inference bottleneck in current fine-grained quantization approaches while maintaining similar accuracies. Integer Scale is
Externí odkaz:
http://arxiv.org/abs/2405.14597
Multimodal information extraction (MIE) gains significant attention as the popularity of multimedia content increases. However, current MIE methods often resort to using task-specific model structures, which results in limited generalizability across
Externí odkaz:
http://arxiv.org/abs/2401.03082
Autor:
Li, Qingyuan, Meng, Ran, Li, Yiduo, Zhang, Bo, Li, Liang, Lu, Yifan, Chu, Xiangxiang, Sun, Yerui, Xie, Yuchen
The large language model era urges faster and less costly inference. Prior model compression works on LLMs tend to undertake a software-centric approach primarily focused on the simulated quantization performance. By neglecting the feasibility of dep
Externí odkaz:
http://arxiv.org/abs/2311.09550
As the size of large language models (LLMs) continues to grow, model compression without sacrificing accuracy has become a crucial challenge for deployment. While some quantization methods, such as GPTQ, have made progress in achieving acceptable 4-b
Externí odkaz:
http://arxiv.org/abs/2309.02784
Autor:
Li, Qingyuan, Zhang, Yifan, Li, Liang, Yao, Peng, Zhang, Bo, Chu, Xiangxiang, Sun, Yerui, Du, Li, Xie, Yuchen
In the era of large-scale language models, the substantial parameter size poses significant challenges for deployment. Being a prevalent compression technique, quantization has emerged as the mainstream practice to tackle this issue, which is mainly
Externí odkaz:
http://arxiv.org/abs/2308.15987
Structured pruning greatly eases the deployment of large neural networks in resource-constrained environments. However, current methods either involve strong domain expertise, require extra hyperparameter tuning, or are restricted only to a specific
Externí odkaz:
http://arxiv.org/abs/2210.00181
Autor:
Li, Chuyi, Li, Lulu, Jiang, Hongliang, Weng, Kaiheng, Geng, Yifei, Li, Liang, Ke, Zaidan, Li, Qingyuan, Cheng, Meng, Nie, Weiqiang, Li, Yiduo, Zhang, Bo, Liang, Yufei, Zhou, Linyuan, Xu, Xiaoming, Chu, Xiangxiang, Wei, Xiaoming, Wei, Xiaolin
For years, the YOLO series has been the de facto industry-level standard for efficient object detection. The YOLO community has prospered overwhelmingly to enrich its use in a multitude of hardware platforms and abundant scenarios. In this technical
Externí odkaz:
http://arxiv.org/abs/2209.02976
Publikováno v:
In Geriatric Nursing July-August 2024 58:388-398
Publikováno v:
In Journal of the Franklin Institute July 2024 361(10)
Autor:
Zheng, Yifan, Zhang, Guodong, Huan, Zhenghao, Zhang, Yang, Yuan, Guangfu, Li, Qingyuan, Ding, Guoyu, Lv, Zhaochen, Ni, Wang, Shao, Yuchuan, Liu, Xingjiang, Zu, Jifeng
Publikováno v:
In Space Solar Power and Wireless Transmission June 2024 1(1):17-26